مروری سیستماتیک بر تحلیل جهات توسعه شهری با استفاده از الگوریتم یادگیری ماشین

Urban development is one of the most dynamic and influential processes, encompassing a wide range of social, economic, and environmental changes that significantly impact human societies and the natural environment. It plays a central role in shaping cities, influencing everything from infrastructure and housing to transportation and public services. As cities continue to grow and evolve, especially in areas experiencing rapid urbanization and demographic shifts, understanding urban development trends becomes increasingly important. This understanding is essential for efficient resource management, sustainable urban planning, and the creation of resilient cities capable of adapting to future challenges. In this context, the application of advanced tools and techniques, such as machine learning algorithms, offers new and unique opportunities to analyze complex urban development patterns. These algorithms, as a subset of artificial intelligence, are capable of processing and analyzing vast amounts of data, enabling the identification of intricate relationships between multiple variables that influence urban growth and change. Machine learning techniques, due to their ability to model non-linear relationships and capture intricate patterns, have become an essential tool in urban studies, particularly in analyzing development trends and identifying the various factors that shape urban development.

Machine learning algorithms offer the potential to provide predictive insights into future urban development patterns by utilizing historical data and identifying key indicators that drive growth, land use changes, and infrastructure demands. Their ability to analyze diverse datasets, including satellite imagery, census data, land use patterns, and social media trends, allows for a more comprehensive understanding of urban dynamics. These algorithms can uncover patterns that are not immediately apparent through traditional analysis methods, offering new perspectives and solutions for urban planning and policy-making. The widespread adoption of machine learning has not only improved our understanding of urban development but has also significantly influenced policy decisions and urban planning practices. By forecasting urban trends, these algorithms can guide policymakers in making informed decisions regarding resource allocation, infrastructure development, environmental protection, and social equity. Additionally, machine learning provides the tools to examine the long-term sustainability of urban development strategies, ensuring that cities grow in a way that is both economically viable and environmentally sustainable.

To provide a deeper understanding of the current state of research in this field, this article presents a systematic review of studies that have employed machine learning techniques to examine urban development trends. By systematically reviewing a broad range of academic literature from databases such as Google Scholar (www.scholar.google.com) and Scopus (www.scopus.com) between 2006 and 2024, we identified 83 relevant studies. These studies were thoroughly analyzed to understand the approaches used, the tools and techniques employed, and the key findings in this area of research. The results of this review are derived from MAXQDA software, a powerful tool used for qualitative data analysis, which helped in organizing, coding, and interpreting the data.

This systematic review not only highlights the various machine learning techniques that have been applied to urban development studies but also provides a comprehensive overview of advancements in this field. It identifies the strengths and limitations of different approaches and discusses the challenges that remain in utilizing machine learning for urban development analysis. The findings contribute valuable insights to the ongoing efforts in urban planning and development, offering a roadmap for future research and practical applications in the design of sustainable and smart cities. Furthermore, the review emphasizes the need for continued collaboration between data scientists, urban planners, and policymakers to ensure that machine learning tools are applied effectively and ethically in shaping urban landscapes. In particular, the integration of machine learning models can help address some of the more pressing challenges that cities face, such as environmental degradation, urban sprawl, and inequality in resource distribution. Additionally, machine learning can contribute to creating more inclusive urban environments by identifying areas of inequality and enabling targeted interventions for marginalized communities.

The review also points to the growing importance of data privacy and security in the context of machine learning in urban planning. As cities become increasingly dependent on data-driven tools, ensuring that personal and sensitive information is protected becomes paramount. This includes addressing ethical concerns related to algorithmic bias, transparency, and accountability. By leveraging diverse datasets and ensuring that machine learning models are well-calibrated, urban development can become more equitable and sustainable. Ultimately, the integration of machine learning into urban development studies promises to enhance decision-making processes, improve urban policy frameworks, and facilitate more effective and sustainable urban growth. By addressing the complexities of urbanization through data-driven approaches, cities can pave the way for smarter, greener, and more inclusive futures.